• Journal of the KSME
• /
• v.32 no.4
• /
• pp.351-357
• /
• 1992

고온 사용 설비의 잔여수명을 진단하는 비파괴적인 여러 가지 방법 중에서 현장에서 간단히 측 정을 함으로써 경년열화 정도를 비교적 쉽게 알아낼 수 있는 경도법에 대하여 살펴보았다. 이 방법은 크립손상 평가뿐만 아니라 피로 손상 평가에도 사용되고 있으며 외국의 경우 현장에서 많이 사용되고 있는, 가장 보편화된 방법 중의 하나이다. 국내의 경우에도 노후화된 고온 사용 설비가 상당수되기 때문에 설비의 안전성이나 경제적인 운용을 위해서 이들의 손상 정도를 정 기적으로 진단할 필요성이 매우 크나 이에 대한 연구 성과는 외국에 비하여 미미한 편이기 때 문에 앞으로 이에 대한 많은 노력이 이루어져야 한다고 생각되나. 특히 현장에서는 휴대용 시 험기를 사용하여야 하나 수명평가에는 비커스 경도값을 사용하고 있기 때문에 이들의 경도 환 산에 대한 D/B 확충이 시급한 실정이다. 또한 기존 기술의 습득 및 손상 평가의 정확도 향상, 새로운 방법들의 개발 그리고 이들의 현장 적용 등을 위해서는 실기 사용재의 입수, 정보교환, 전문가시스템(expert system) 개발을 위한 D/B 구축 등 산 . 학 . 연의 협동이 절실히 요구된다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.05a
• /
• pp.238-242
• /
• 2007

자동차의 고장은 그 종류나 특징면에서 다양하게 나타나게 되므로 자동차의 진단과 점검에는 많은 노동력과 비용, 시간이 소요되며 운전자에 의한 정보를 기대하기 힘든 경우에는 진단이나 정비과정에 많은 어려움을 겪게 된다. 따라서 본 연구에서는 운전자에 의한 일반적인 정보와 진동 소음센서에 의한 정보의 신호처리기술을 종합하여 자동차 부품의 이상 신호 분석을 하였다. 그리고 정상 상태 대비 이상 신호에 따른 진동 소음 데이터 변화율을 계산하여 작동 모드 별 실내음압에 영향을 미치는 신호 및 해당 주파수 특성을 분석하였다. 이에 따라 자동차 정비 전문가 시스템 구축을 위한 기초 연구로 엔진부의 이상 신호와 각 부품 별 이상 신호로 나누어 분석하여 데이터 처리 과정 및 이상 증상 별 경향 파악에 본 연구의 목적을 둔다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.05a
• /
• pp.243-246
• /
• 2007

자동차의 고장은 그 종류나 특징 면에서 다양하게 나타나게 되므로 자동차의 진단과 점검에는 많은 노력과 비용, 시간이 소요되며 운전자에 의한 정보를 기대하기 힘든 경우에는 진단이나 정비과정에 많은 어려움을 겪게 된다. 따라서 본 연구에서는 운전자에 의한 일반적인 정보와 진동 소음 센서에 의한 정보의 신호처리기술을 종합하여 자동차 부품의 이상 신호 분석을 하였다. 그리고 정상 상태 대비 이상 신호에 따른 진동 소음 데이터 변화율을 계산하여 작동 모드 별 실내 음압에 영향을 미치는 신호 및 해당 주파수 특성을 분석하였다. 이에 따라 자동차 정비 전문가 시스템 구축을 위한 기초 연구로 엔진부의 이상 신호와 각 부품 별 이상 신호로 나누어 분석하여 데이터 처리 과정 및 이상 증상 별 경향 파악에 본 연구의 목적을 둔다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.430-434
• /
• 2001

Virtual manufacturing system is integrated computer model that represents the precise and whole structure of manufacturing system and simulates its physical and logical behavior in operation.[1] A virtual machine is computer model that represents a CNC machine tool and one of core elements of virtual manufacturing system. In this paper, it is emphasized that a virtual machine must be web-based system for serving information to all attendants in a real machine tool without the restriction of time or location, and then in the fault diagnosis, one of important modules of a virtual machine, the methods of both using the controller signal and web-based expert system are proposed.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.109-114
• /
• 1997

As CNC machine tool is one of core elements of manufacturing system, it is much important that it remains without troubleshoots. As a virtual machine is a recent alternative using IT for optimal utilization of CNC machine tool, it is a computer model that represents a CNC machine tool. But a virtual machine is still conceptual. So, in this paper, it is proposed that a virtual machine be a realistic model in the fault diagnosis module. For this purpose, the fault diagnosis system of machine tool using CORBA and fault diagnosis expert system has been implemented. Using this system, we have expections to diagnose exactly and prompty without the restriction of time or location, to reduce MTTR(Mean Time To Repair) and finally to increase the availability of manufacturing system.

• Tribology and Lubricants
• /
• v.17 no.3
• /
• pp.244-250
• /
• 2001

A rotating axis diagnostic system supported with journal bearing has been established that has been widely used in the industry. In order to measure the most sensitive signals that would be generated in the abnormal operation, sensors which measure AE(acoustic emission), gap and acceleration have been attached at the various location on the experimental apparatus. Data were obtained in the steady state operational condition of the system which was verified through the empirical measurement. Notable discrepancies were observed in RMS acceleration signal which could be utilized to predict the undesirable operational condition of the system.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.8 no.4
• /
• pp.185-193
• /
• 2004

Reasonable prediction of bridge deterioration is the most important factor in the determination of repair time or optimized maintenance policy for bridges. To accomplish these purposes, the proposed method is composed of quantitative condition assessment, Markov chains and Bayesian estimates. Example predictions of concrete slab bridges in Korea were illustrated with higher reasonability than those of existing methods such as expert opinion and visual inspection only.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.5
• /
• pp.1-12
• /
• 2015

Length and the number of tunnels has increased 10% annually. Tunnel construction has positive effect in nature and driving condition. However, the structure of tunnels lead to a greater probability of major accidents. For this reason, tunnel is focusing its attention on the rapid incident handling and disaster management to build a tunnel management system in recently. In this study, tunnel management system adequacy analyzed in terms of operational safety using IPA and AHP analysis. IPA analysis results using the portfolio chart, incident management factors has a large gap between important and satisfaction. Disaster management is analyzed high ranking in priority. However, incident management factors are derived first priority in AHP analysis. This study determined that the results are meaningful to practitioners in the field is determined. In addition, practitioners comments should be reflected primarily for tunnel operational safely.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.3
• /
• pp.233-240
• /
• 2004

Purpose: We developed a computer-aided classifier using artificial neural network (ANN) to discriminate the cerebral metabolic pattern of medial and lateral temporal lobe epilepsy (TLE). Materials and Methods: We studied brain F-18-FDG PET images of 113 epilepsy patients sugically and pathologically proven as medial TLE (left 41, right 42) or lateral TLE (left 14, right 16). PET images were spatially transformed onto a standard template and normalized to the mean counts of cortical regions. Asymmetry indices for predefined 17 mirrored regions to hemispheric midline and those for medial and lateral temporal lobes were used as input features for ANN. ANN classifier was composed of 3 independent multi-layered perceptrons (1 for left/right lateralization and 2 for medial/lateral discrimination) and trained to interpret metabolic patterns and produce one of 4 diagnoses (L/R medial TLE or L/R lateral TLE). Randomly selected 8 images from each group were used to train the ANN classifier and remaining 51 images were used as test sets. The accuracy of the diagnosis with ANN was estimated by averaging the agreement rates of independent 50 trials and compared to that of nuclear medicine experts. Results: The accuracy in lateralization was 89% by the human experts and 90% by the ANN classifier Overall accuracy in localization of epileptogenic zones by the ANN classifier was 69%, which was comparable to that by the human experts (72%). Conclusion: We conclude that ANN classifier performed as well as human experts and could be potentially useful supporting tool for the differential diagnosis of TLE.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.6
• /
• pp.457-464
• /
• 2004

Hard Disk Drive (HDD) test system is an equipment for the final test of HDD product by iterative read/write/seek test. This paper proposes an expert system for the fault diagnosis of HDD test systems. The purposed expert system is composed with two cascade inference, fuzzy logic and conventional binary logic. The fuzzy logic determines the possibility of the system fault using the test history data, then, the binary logic inferences the fault location of the test system. The proposed expert system is tested in SAMSUNG HDD production line, KUMI, KOREA, and shows satisfactory results.